Commit
•
d040f32
1
Parent(s):
bec2539
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: petro-twitter-assistant-30ep-large
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# petro-twitter-assistant-30ep-large
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [flax-community/gpt-2-spanish](https://huggingface.co/flax-community/gpt-2-spanish) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 3.3050
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0001
|
| 36 |
+
- train_batch_size: 22
|
| 37 |
+
- eval_batch_size: 22
|
| 38 |
+
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 2
|
| 40 |
+
- total_train_batch_size: 44
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_steps: 100
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 3.4824 | 0.73 | 1000 | 3.3659 |
|
| 52 |
+
| 3.2393 | 1.46 | 2000 | 3.2667 |
|
| 53 |
+
| 3.113 | 2.19 | 3000 | 3.2174 |
|
| 54 |
+
| 3.0121 | 2.92 | 4000 | 3.1767 |
|
| 55 |
+
| 2.9076 | 3.65 | 5000 | 3.1619 |
|
| 56 |
+
| 2.8358 | 4.38 | 6000 | 3.1665 |
|
| 57 |
+
| 2.7708 | 5.11 | 7000 | 3.1874 |
|
| 58 |
+
| 2.6846 | 5.84 | 8000 | 3.1695 |
|
| 59 |
+
| 2.6092 | 6.57 | 9000 | 3.2114 |
|
| 60 |
+
| 2.5487 | 7.3 | 10000 | 3.2517 |
|
| 61 |
+
| 2.4942 | 8.04 | 11000 | 3.3050 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.20.1
|
| 67 |
+
- Pytorch 1.12.0
|
| 68 |
+
- Datasets 2.1.0
|
| 69 |
+
- Tokenizers 0.12.1
|